Security audit
Company Values
Security checks for vulnerabilities and agentic risk
Overview
The skills are mostly coherent maintainer and Convex workflow helpers, but one review helper defaults to running nested Codex with full filesystem/sandbox bypass authority.
Review before installing if you do not want a skill that can run nested Codex in full-access mode by default. For safer use, set `AUTOREVIEW_YOLO=0` or pass `--no-yolo`, and only use the moderation and PR-maintainer skills with the intended ClawHub accounts, explicit targets, and confirmation for writes.
Vulnerability Patterns
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Static analysis
No suspicious patterns detected.